© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 157864
    Prev
    Next
    INDEX
    Explanations

    articles and phrases with specific follow-ups

    np_acts-logits-general · gemini-2.5-flash-lite

    Sceletium alkaloids

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Matter
    0.51
    antly
    0.50
     ها
    0.46
     특
    0.46
     પોતાના
    0.45
    きました
    0.44
     hallmark
    0.44
     ミ
    0.43
     المط
    0.43
    вим
    0.43
    POSITIVE LOGITS
    做
    0.47
     अकादमी
    0.47
     Django
    0.47
     Osc
    0.46
     Muslim
    0.45
     Iraq
    0.45
     crappy
    0.44
     dummies
    0.44
     Replica
    0.43
     Elev
    0.43
    Activations Density 0.000%

    No Known Activations